GLM-Zero-Preview is Zhizhu's first reasoning model trained based on advanced reinforcement learning technology, focusing on enhancing AI reasoning abilities, excelling in mathematical logic, code handling, and complex issues requiring deep reasoning. Compared to its base model, it significantly improves expert task performance without a major compromise on general task capabilities. Its performance is on par with OpenAI's o1-preview in evaluations such as AIME 2024, MATH500, and LiveCodeBench. Zhizhu Huazhang Technology Co., Ltd. is dedicated to enhancing model capabilities through reinforcement learning technology, and will soon launch the official version of GLM-Zero, expanding deep thinking capabilities across more technical fields.